1 and 2. Look at the chapter on interactive graphics and, specifically, the code to display a subject's MRICloud data as a sunburst plot. Do the following. Display this subject's data as a Sankey diagram. Display as many levels as you can for type = 1, starting from the intracranial volume. Put this in a file called hw4.ipynb.

import pandas as pd
import plotly.express as px
import numpy as np
import os
import plotly.graph_objects as go

## load in the hierarchy information
url = "https://raw.githubusercontent.com/bcaffo/MRIcloudT1volumetrics/master/inst/extdata/multilevel_lookup_table.txt"
multilevel_lookup = pd.read_csv(url, sep = "\t").drop(['Level5'], axis = 1)
multilevel_lookup = multilevel_lookup.rename(columns = {
    "modify"   : "roi", 
    "modify.1" : "level4",
    "modify.2" : "level3", 
    "modify.3" : "level2",
    "modify.4" : "level1"})
multilevel_lookup = multilevel_lookup[['roi', 'level4', 'level3', 'level2', 'level1']]
multilevel_lookup.head()

	roi	level4	level3	level2	level1
0	SFG_L	SFG_L	Frontal_L	CerebralCortex_L	Telencephalon_L
1	SFG_R	SFG_R	Frontal_R	CerebralCortex_R	Telencephalon_R
2	SFG_PFC_L	SFG_L	Frontal_L	CerebralCortex_L	Telencephalon_L
3	SFG_PFC_R	SFG_R	Frontal_R	CerebralCortex_R	Telencephalon_R
4	SFG_pole_L	SFG_L	Frontal_L	CerebralCortex_L	Telencephalon_L

## Now load in the subject data
id = 127
subjectData = pd.read_csv("kirby21AllLevels.csv")
subjectData = subjectData.loc[(subjectData.type == 1) & (subjectData.level == 5) & (subjectData.id == id)]
# Show only this subject's region (ROI) and volume 
subjectData = subjectData[['roi', 'volume']]
## Merge the subject data with the multilevel data
subjectData = pd.merge(subjectData, multilevel_lookup, on = "roi")
subjectData = subjectData.assign(icv = "ICV")
subjectData = subjectData.assign(comp = subjectData.volume / np.sum(subjectData.volume))
subjectData.head()

	roi	volume	level4	level3	level2	level1	icv	comp
0	SFG_L	12926	SFG_L	Frontal_L	CerebralCortex_L	Telencephalon_L	ICV	0.009350
1	SFG_R	10050	SFG_R	Frontal_R	CerebralCortex_R	Telencephalon_R	ICV	0.007270
2	SFG_PFC_L	12783	SFG_L	Frontal_L	CerebralCortex_L	Telencephalon_L	ICV	0.009247
3	SFG_PFC_R	11507	SFG_R	Frontal_R	CerebralCortex_R	Telencephalon_R	ICV	0.008324
4	SFG_pole_L	3078	SFG_L	Frontal_L	CerebralCortex_L	Telencephalon_L	ICV	0.002227

subjectData = subjectData.drop(['volume'], axis=1)

df2=subjectData.groupby(['icv', 'level1'], as_index=False)['comp'].count()
df2.head()
df3=subjectData.groupby(['level1', 'level2'], as_index=False)['comp'].count()
df3.head()
df4=subjectData.groupby(['level2','level3'], as_index=False)['comp'].count()
df4.head()
df5=subjectData.groupby(['level3','level4'], as_index=False)['comp'].count()
df5.head()
df6=subjectData.groupby(['level4','roi'], as_index=False)['comp'].count()
df6.head()

	level4	roi	comp
0	AG_L	AG_L	1
1	AG_R	AG_R	1
2	ALIC_L	ALIC_L	1
3	ALIC_R	ALIC_R	1
4	Amyg_L	Amyg_L	1

df2.columns = ['a', 'b', 'comp']
df3.columns = ['a', 'b', 'comp']
df4.columns = ['a', 'b', 'comp']
df5.columns = ['a', 'b', 'comp']
df6.columns = ['a', 'b', 'comp']
df7 = df2.append(df3)
df8 = df7.append(df4)
df9 = df8.append(df5)
df10 = df9.append(df6)
df10

	a	b	comp
0	ICV	CSF	32
1	ICV	Diencephalon_L	8
2	ICV	Diencephalon_R	8
3	ICV	Mesencephalon	8
4	ICV	Metencephalon	20
...	...	...	...
269	midbrain_R	Midbrain_R	1
270	midbrain_R	RedNc_R	1
271	midbrain_R	Snigra_R	1
272	post_DPWM_L	PCR_L	1
273	post_DPWM_R	PCR_R	1

500 rows × 3 columns

import chart_studio.plotly as py

def genSankey(df,cat_cols=[],value_cols='',title='Sankey Diagram'):
    # maximum of 6 value cols -> 6 colors
    colorPalette = ['#FFD43B','#646464','#4B8BBE','#306998']
    labelList = []
    colorNumList = []
    for catCol in cat_cols:
        labelListTemp =  list(set(df[catCol].values))
        colorNumList.append(len(labelListTemp))
        labelList = labelList + labelListTemp
        
    # remove duplicates from labelList
    labelList = list(dict.fromkeys(labelList))
    
    # define colors based on number of levels
    colorList = []
    for idx, colorNum in enumerate(colorNumList):
        colorList = colorList + [colorPalette[idx]]*colorNum
        
    # transform df into a source-target pair
    for i in range(len(cat_cols)-1):
        if i==0:
            sourceTargetDf = df[[cat_cols[i],cat_cols[i+1],value_cols]]
            sourceTargetDf.columns = ['source','target','count']
        else:
            tempDf = df[[cat_cols[i],cat_cols[i+1],value_cols]]
            tempDf.columns = ['source','target','count']
            sourceTargetDf = pd.concat([sourceTargetDf,tempDf])
        sourceTargetDf = sourceTargetDf.groupby(['source','target']).agg({'count':'sum'}).reset_index()
        
    # add index for source-target pair
    sourceTargetDf['sourceID'] = sourceTargetDf['source'].apply(lambda x: labelList.index(x))
    sourceTargetDf['targetID'] = sourceTargetDf['target'].apply(lambda x: labelList.index(x))
    
    # creating the sankey diagram
    data = dict(
        type='sankey',
        node = dict(
          pad = 15,
          thickness = 20,
          line = dict(
            color = "black",
            width = 0.5
          ),
          label = labelList,
          color = colorList
        ),
        link = dict(
          source = sourceTargetDf['sourceID'],
          target = sourceTargetDf['targetID'],
          value = sourceTargetDf['count']
        )
      )
    
    layout =  dict(
        title = title,
        font = dict(
          size = 10
        )
    )
       
    fig = dict(data=[data], layout=layout)
    return fig

import plotly

fig = go.Figure(genSankey(df10,
                cat_cols=['a','b'],
                value_cols='comp',
                title='Sankey Diagram of Brain Regions'),
               )
fig.update_layout(
    autosize=False,
    width=1000,
    height=2000,
    paper_bgcolor="LightSteelBlue",
)
#plotly.offline.plot(fig, validate=False)
fig.show()

#fig.to_html()

1. Link to website: https://eyuasa.github.io/

1. Create the opioid sqlite database from https://smart-stats.github.io/ds4bio_book/book/_build/html/sqlite.html. However, only go to the step where the csv files are read into the database. Then exit sqlite and you should have a file opioid.db that has the data. Next, read the three tables into pandas dataframes and do the data wrangling from the sqlite chapter directly in pandas. Add the python code to your hw4.ipynb file.